2 * rhynodge - ComicFilter.java - Copyright © 2013 David Roden
4 * This program is free software: you can redistribute it and/or modify
5 * it under the terms of the GNU General Public License as published by
6 * the Free Software Foundation, either version 3 of the License, or
7 * (at your option) any later version.
9 * This program is distributed in the hope that it will be useful,
10 * but WITHOUT ANY WARRANTY; without even the implied warranty of
11 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
12 * GNU General Public License for more details.
14 * You should have received a copy of the GNU General Public License
15 * along with this program. If not, see <http://www.gnu.org/licenses/>.
18 package net.pterodactylus.rhynodge.filters;
20 import static com.google.common.base.Preconditions.checkArgument;
23 import java.net.URISyntaxException;
24 import java.util.List;
26 import net.pterodactylus.rhynodge.Filter;
27 import net.pterodactylus.rhynodge.State;
28 import net.pterodactylus.rhynodge.states.ComicState;
29 import net.pterodactylus.rhynodge.states.ComicState.Comic;
30 import net.pterodactylus.rhynodge.states.ComicState.Strip;
31 import net.pterodactylus.rhynodge.states.HtmlState;
33 import com.google.common.base.Optional;
34 import org.jsoup.nodes.Document;
37 * {@link Filter} implementation that can extract {@link ComicState}s from
40 * @author <a href="mailto:bombe@pterodactylus.net">David ‘Bombe’ Roden</a>
42 public abstract class ComicSiteFilter implements Filter {
45 public State filter(State state) {
46 checkArgument(state instanceof HtmlState, "state must be an HTML state");
48 /* initialize states: */
49 HtmlState htmlState = (HtmlState) state;
50 ComicState comicState = new ComicState();
53 Optional<String> title = extractTitle(htmlState.document());
54 List<String> imageUrls = extractImageUrls(htmlState.document());
55 List<String> imageComments = extractImageComments(htmlState.document());
57 /* store comic, if found, into state. */
58 if (title.isPresent() && !imageUrls.isEmpty()) {
59 Comic comic = new Comic(title.get());
61 for (String imageUrl : imageUrls) {
62 String imageComment = (imageCounter < imageComments.size()) ? imageComments.get(imageCounter) : "";
64 URI stripUri = new URI(htmlState.uri()).resolve(imageUrl);
65 Strip strip = new Strip(stripUri.toString(), imageComment);
68 } catch (URISyntaxException use1) {
69 throw new IllegalStateException(String.format("Could not resolve image URL “%s” against base URL “%s”.", imageUrl, htmlState.uri()), use1);
72 comicState.add(comic);
83 * Extracts the title of the comic from the given document.
86 * The document to extract the title from
87 * @return The extracted title, or {@link Optional#absent()}} if no title could
90 protected abstract Optional<String> extractTitle(Document document);
93 * Extracts the image URLs from the given document.
96 * The document to extract the image URLs from
97 * @return The extracted image URLs, or an empty list if no URLs could be
100 protected abstract List<String> extractImageUrls(Document document);
103 * Extracts the image comments from the given document. The elements of this
104 * last and of the list returned by {@link #extractImageUrls(org.jsoup.nodes.Document)}
105 * are paired up and added as {@link Strip}s. If the list returned by this
106 * method has less elements, an empty string is used for the remaining images.
109 * The document to extract the image comments from
110 * @return The extracted image comments
112 protected abstract List<String> extractImageComments(Document document);